| { | |
| "_name_or_path": "LazarusNLP/IndoNanoT5-base", | |
| "adapters": { | |
| "adapters": {}, | |
| "config_map": {}, | |
| "fusion_config_map": {}, | |
| "fusions": {} | |
| }, | |
| "architectures": [ | |
| "T5AdapterModel" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "id2label": null, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "label2id": null, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "prediction_heads": { | |
| "default": { | |
| "activation_function": null, | |
| "bias": false, | |
| "head_type": "seq2seq_lm", | |
| "label2id": null, | |
| "layer_norm": false, | |
| "layers": 1, | |
| "shift_labels": false, | |
| "vocab_size": 32128 | |
| } | |
| }, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |